The 2nd Anti-UAV Workshop & Challenge


Oct 11 Afternoon, 2021 Virtual



Schedule

Zoom ID: 873 8376 0591, Join Us!

Date Oct 11, 2021 Speaker Topic
14:30-14:40 Opening Remarks and Welcome
14:40-15:10 The 2nd Anti-UAV challenge introduction and results
15:10-15:25 Oral talk 1: 1st-Place Award of the 2nd Anti-UAV Challenge
15:25-15:55 Professor at Stony Brook University Haibin Ling Invited talk 1: Visual Object Tracking Algorithms and Benchmarks
15:55-16:10 Oral talk 2: 2nd-Place Award of the 2nd Anti-UAV Challenge
16:10-16:40 Poster session and coffee break
16:40-17:10 Postdoc research fellow at Berkeley AI Research Lab (BAIR), EECS, UC Berkeley Shanghang Zhang Invited talk 2: Learning with less labels
17:10-17:25 Oral talk 3: 3rd-Place Award of the 2nd Anti-UAV Challenge
17:25-17:40 Oral talk 4: Best Paper Award
17:40-18:00 Awards & Future Plans


Description of the 2nd Anti-UAV Workshop & Challenge

Civil unmanned aerial vehicle (UAV) is growing rapidly in a wide range of consumer communications and networks with their autonomy, flexibility, and a broad range of application domains. UAV applications offer possible civil and public domain applications in which single or multiple UAVs may be used. Nevertheless, we should also be aware of the potential threat to our lives caused by UAV intrusion, since UAVs can also be used to conduct physical attacks (e.g., via explosives) and cyber-attacks (e.g., hacking a critical infrastructure). Moreover, unauthorized UAVs are a danger to civilian aircraft. There have been multiple instances of drone sightings halted air traffic at airports, leading to significant economic losses for airlines.

Historically, radar is certainly a very powerful technology for detecting traditional incoming airborne threats. However, these comparatively small drones are difficult for radar to accurately detect, because they have very small radar cross-sections and erratic flight paths. Therefore, how to use computer vision algorithms to perceive UAVs is a crucial part of the whole UAV-defense system.

Traditional computer vision research for UAV detection and tracking lacks a high-quality benchmark in dynamic environments. To mitigate this gap, we held the 1st International Workshop on Anti-UAV Challenge at CVPR 2020, releasing a dataset consisting of 160 video sequences (both RGB and infrared). The workshop attracted attention from researchers all over the world. Many submitted solutions outperform the baseline method, making great contributions to addressing the anti-UAV problem. The 2nd anti-UAV challenge extends the benchmark dataset to 250 high-quality, full HD thermal infrared video sequences, spanning multiple occurrences of multi-scale (i.e., large, small and tiny, as shown in Fig. 1) UAVs. The workshop encourages participants to develop automated methods that can detect and track UAVs in thermal infrared videos with high accuracy. Particularly, algorithms that can detect and track fast-moving drones in complex environments (e.g., occlusion by cloud/buildings/trees, and fake targets like kites, balloons, birds, etc.) are highly expected.

This workshop will bring together academic and industrial experts in the field of UAVs to discuss the techniques and applications of tracking UAVs. Participants are invited to submit their original contributions, surveys, and case studies that address the works of UAV’s detection and tracking issues.

a b c

Figure 1 Illustrations of civil UAVs. (a) Large civil UAV; (b) Small civil UAV; (c) Tiny civil UAV.


Topics of interest

The submissions are expected to deal with visual perception and processing tasks which include but are not limited to:

  • Applications of computer vision on UAVs
  • Strategies for searching of UAVs based on NIR and/or VIS data
  • Spectrum sensing techniques for UAVs detection
  • Localization and open-set identification of UAVs
  • Scene understanding for UAVs
  • Small/tiny object detection and tracking techniques
  • Fine-grained object recognition
  • Real-time deep learning inference
  • Infrared image and video analysis


Contact

Please feel free to send any question or comments to: zhaojian90@u.nus.edu, g_wang@foxmail.com, lijianan@bit.edu.cn.

SPONSORS